{"total":25,"rows":[{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37,"area":null},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2406.19760","title":"Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2601.16669","title":"PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice","created":"2026-01-23","cited_by_count":15,"area":null},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2403.18435","title":"DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2502.17943","title":"CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2404.00990","title":"Exploring the Nexus of Large Language Models and Legal Systems: A Short Survey","created":"2024-04-01","cited_by_count":6,"area":null},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2505.23832","title":"LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2512.04578","title":"LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2605.10186","title":"LegalCiteBench: Evaluating Citation Reliability in Legal Language Models","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2503.04305","title":"Computational Law: Datasets, Benchmarks, and Ontologies","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2507.18455","title":"LLM-based Embedders for Prior Case Retrieval","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2606.09389","title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2601.15267","title":"Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2608.18752","title":"GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2502.11131","title":"Improving Similar Case Retrieval Ranking Performance By Revisiting RankSVM","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2511.05000","title":"Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.23779","title":"GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2606.09632","title":"Civil Court Simulation with Large Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.32770","title":"C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36965","title":"Chinese-Jev: Bringing System One Model to Chinese-Language Tasks","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}